Triple

T1036576
Position Surface form Disambiguated ID Type / Status
Subject Vivienne Haigh-Wood Eliot E22376 entity
Predicate givenName P17 FINISHED
Object Vivienne
Vivienne was a British writer and socialite best known as the first wife of poet T. S. Eliot and a central, troubled figure in his life and work.
 E122089 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Vivienne | Statement: [Vivienne Haigh-Wood Eliot, givenName, Vivienne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vivienne
Context triple: [Vivienne Haigh-Wood Eliot, givenName, Vivienne]
  • A. Vivian
    Vivian "Buster" Burey Marshall was a civil rights activist and the first wife of U.S. Supreme Court Justice Thurgood Marshall.
  • B. Vanessa
    Vanessa is an English feminine given name that gained wider recognition through public figures such as Vanessa Trump.
  • C. Carine
    Carine is a feminine given name, often considered a variant of names like Catherine or Karine, used in various European languages.
  • D. Jane Avril
    Jane Avril is a famous poster by French artist Henri de Toulouse-Lautrec depicting the celebrated can-can dancer of the Moulin Rouge.
  • E. Vera
    Vera Rubin was an influential American astronomer whose pioneering work on galaxy rotation curves provided key evidence for the existence of dark matter.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Vivienne
Triple: [Vivienne Haigh-Wood Eliot, givenName, Vivienne]
Generated description
Vivienne was a British writer and socialite best known as the first wife of poet T. S. Eliot and a central, troubled figure in his life and work.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vivienne
Target entity description: Vivienne was a British writer and socialite best known as the first wife of poet T. S. Eliot and a central, troubled figure in his life and work.
  • A. Vivian
    Vivian "Buster" Burey Marshall was a civil rights activist and the first wife of U.S. Supreme Court Justice Thurgood Marshall.
  • B. Vanessa
    Vanessa is an English feminine given name that gained wider recognition through public figures such as Vanessa Trump.
  • C. Carine
    Carine is a feminine given name, often considered a variant of names like Catherine or Karine, used in various European languages.
  • D. Jane Avril
    Jane Avril is a famous poster by French artist Henri de Toulouse-Lautrec depicting the celebrated can-can dancer of the Moulin Rouge.
  • E. Vera
    Vera Rubin was an influential American astronomer whose pioneering work on galaxy rotation curves provided key evidence for the existence of dark matter.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a493d848848190aed4011b34b2e8d3 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b82a1014819085bfc077e24c9742 completed March 1, 2026, 10:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3bc378fc8190846d5ffce73371dd completed March 7, 2026, 2:52 p.m.
NEDg Description generation batch_69ac3df28858819091c594a9cb2aab07 completed March 7, 2026, 3:02 p.m.
NED2 Entity disambiguation (via description) batch_69ac3e5b716c8190b95fde14ee6c434a completed March 7, 2026, 3:03 p.m.
Created at: March 1, 2026, 7:41 p.m.